SmartTokenGuard

Stop burning credits on broken AI video.

CommunityOnlineAPI key requiredGlobalFreeRead-only

What it can do

  • Stg Pricing: Plans, prices and checkout links for SmartTokenGuard. No license needed.
  • Stg Account: The license's plan, checks used and checks remaining this month.
  • Stg Inspect Media Url: Measure a rendered image or video at a public https URL (max 32 MB / 60 s / 1080p): blur, exposure, black and frozen frames, flicker, cuts, impacts and colour/lighting drift aga

What data it sees

Do you need an account

An API key from the service settings is required

Stop burning credits on broken AI video.

Every black frame, frozen shot and off-model keyframe is money you already paid for. Pass a keyframe or clip by https URL and SmartTokenGuard tells your agent whether it's worth paying for the next step: PASS, RETRY with exact negative-prompt terms, lower motion and a new seed, SWITCH to a fallback model, or HALT a shot that keeps failing.

  • Check the keyframe first and skip paying for clips built on a bad still
  • Catch black frames, freezes, flicker, blur and colour drift instantly
  • Review frames for hands and faces before anything passes
  • Budget caps and spend per shot

Starter US$9/month (300 checks), Pro US$29/month (3,000 checks). Run your numbers and get a key: https://nwjnjjj.github.io/smart-token-guard/

How to connect

How to connect SmartTokenGuard to Claude

The server address to paste into Claude settings:

https://smart-token-guard--smarttokenguard.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect SmartTokenGuard to ChatGPT

The server address to paste into ChatGPT settings:

https://smart-token-guard--smarttokenguard.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect SmartTokenGuard to Cursor

The server address to paste into Cursor settings:

https://smart-token-guard--smarttokenguard.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (4)

Raw names from tools/list. Only developers need these.

stg_pricingPlans, prices and checkout links for SmartTokenGuard. No license needed.
stg_accountThe license's plan, checks used and checks remaining this month.
stg_inspect_media_url Measure a rendered image or video at a public https URL (max 32 MB / 60 s / 1080p): blur, exposure, black and frozen frames, flicker, cuts, impacts and colour/lighting drift against reference_image_url. Uses 1 check. Returns a JSON report plus review frames to check for anatomy/identity defects before calling stg_qa_gate.
stg_qa_gate PASS / NEEDS_VISUAL_REVIEW / RETRY_SAME_MODEL / SWITCH_TO_FALLBACK / HALT / HALT_BUDGET with concrete fixes. Stateless: pass earlier attempts for this shot in shot_history (each result's record_this_attempt). Free.
SmartTokenGuard: connect to Claude, ChatGPT, Cursor · Connectors.fun